Skip to content
Agentmart
Submit a tool

feature

Orchestrates feature development with TDD + adversarial convergence via autonomous feedback loops.

Skill by bmschwartz

IndexedLicense unknown
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/bmschwartz-feature

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Orchestrates feature development with TDD + adversarial convergence via autonomous feedback loops. Explores codebase, writes specs, builds test-first, and converges via /deep-review verdicts. Use when the user wants to implement a new feature, says "new feature", "I want to implement", "let's build", or describes functionality to add. Scales by feature tier (Light/Standard/Critical) with configurable autonomy.

Use cases: testing

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/feature

Tools it pre-approves 10

From allowed-tools in SKILL.md: the agent may use these without asking you each time.

  • Read,
  • Grep,
  • Glob,
  • Write,
  • Edit,
  • Bash(git
  • *,
  • mkdir
  • date
  • *)

What's inside

Skill name
feature
Description
Orchestrates feature development with TDD + adversarial convergence via autonomous feedback loops. Explores codebase, writes specs, builds test-first, and converges via /deep-review verdicts. Use when the user wants to implement a new feature, says "new feature", "I want to implement", "let's build", or describes functionality to add. Scales by feature tier (Light/Standard/Critical) with configurable autonomy.
License
unknown
Allowed tools
Read,, Grep,, Glob,, Write,, Edit,, Bash(git, *,, mkdir, *,, date, *)
Instructions
176 lines in SKILL.md · view on GitHub

Before installing

  • Pre-approves some shell commands

Files (8)

  • SKILL.md
  • complete.md · phases/
  • design.md · phases/
  • explore.md · phases/
  • implement.md · phases/
  • verify.md · phases/
  • checkpoint.md · references/
  • spec-template.md · references/

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from bmschwartz/claude-files

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 18, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
Repository
github.com/bmschwartz/claude-files
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from bmschwartz

Cite this page

feature skill. Agent Mart. https://agentmart.dev/skills/bmschwartz-feature (last updated 2026-10-24)